A characterization of the alpha-connections on the statistical manifold of multivariate normal distributions

Abstract

We study a statistical manifold (N, gF, ∇A, ∇A*) of multivariate normal distributions, where gF is the Fisher metric and ∇A is the Amari-Chentsov connection and ∇A* is its conjugate connection. We will show that it admits a solvable Lie group structure and moreover the Amari-Chentsov connection ∇A on (N, gF) will be characterized by the conjugate symmetry, i.e., a curvatures identity R=R* of a connection ∇ and its conjugate connection ∇*.

0

Turn this paper into a lesson

ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.

Discussion (0)

Sign in to join the discussion.

Loading comments…